In this study, we focused on the fact that the color information of an image has a significant effect on the emotion recalled, and we created a dataset with discrete and continuous emotion labels for color and grayscale image pairs, which are not present in existing emotion image datasets. As a result of the analysis of the continuous-valued emotion labels, we found that the color images evoked a wider range of positive and negative emotions. We also conducted experiments to transform the color of the image to the target emotion using the emotion label and the image as input and succeeded in changing the color of the entire image according to the input emotion value. Another experiment is conducted to convert the emotion category and we confirmed that the image was generated in such a way that the evoked emotion was changed compared to the original image.
{"title":"Color-Grayscale-Pair Image Sentiment Dataset and Its Application to Sentiment-Driven Image Color Conversion","authors":"A. Takada, Xueting Wang, T. Yamasaki","doi":"10.1145/3463946.3469240","DOIUrl":"https://doi.org/10.1145/3463946.3469240","url":null,"abstract":"In this study, we focused on the fact that the color information of an image has a significant effect on the emotion recalled, and we created a dataset with discrete and continuous emotion labels for color and grayscale image pairs, which are not present in existing emotion image datasets. As a result of the analysis of the continuous-valued emotion labels, we found that the color images evoked a wider range of positive and negative emotions. We also conducted experiments to transform the color of the image to the target emotion using the emotion label and the image as input and succeeded in changing the color of the entire image according to the input emotion value. Another experiment is conducted to convert the emotion category and we confirmed that the image was generated in such a way that the evoked emotion was changed compared to the original image.","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82853603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Session details: Invited Talk","authors":"Min-Chun Hu","doi":"10.1145/3483205","DOIUrl":"https://doi.org/10.1145/3483205","url":null,"abstract":"","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79701992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the 2021 International Joint Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia 2021","authors":"","doi":"10.1145/3463946","DOIUrl":"https://doi.org/10.1145/3463946","url":null,"abstract":"","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74987091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this talk, I will first give a brief overview of recent deep learning-based approaches for automatic music generation in the symbolic domain. I will then talk about our own research that employs self-attention based architectures, a.k.a. Transformers, for symbolic music generation. A naive approach with Transformers would treat music as a sequence of text-like tokens. But, our research demonstrates that Transformers can generate higher-quality music when music is not treated simply as text. In particular, our Pop Music Transformer model, published at ACM Multimedia 2020, employs a novel beat-based representation of music that informs self-attention models with the bar-beat metrical structure present in music. This approach greatly improves the rhythmic structure of the generated music. A more recent model we published at AAAI 2021, named the Compound Word Transformer, exploits the fact that a musical note is associated with multiple attributes such as pitch, duration and velocity. Instead of predicting tokens corresponding to these different attributes one-by-one at inference time, the Compound Word Transformer predicts them altogether jointly, greatly reducing the sequence length needed to model a full-length song and also making it easier to model the dependency among these attributes.
在这次演讲中,我将首先简要概述最近在符号领域中基于深度学习的自动音乐生成方法。然后我将谈论我们自己的研究,使用基于自我关注的架构,也就是变形金刚,来生成符号音乐。对于《变形金刚》,一种幼稚的方法是将音乐视为一系列类似文本的符号。但是,我们的研究表明,当音乐不被简单地视为文本时,变形金刚可以产生更高质量的音乐。特别是,我们在ACM Multimedia 2020上发表的流行音乐转换器模型,采用了一种新颖的基于节拍的音乐表示,将音乐中存在的小节节奏结构告知自我注意模型。这种方法极大地改善了生成音乐的节奏结构。我们在AAAI 2021上发布了一个最新的模型,名为Compound Word Transformer,它利用了一个音符与多个属性(如音高、持续时间和速度)相关的事实。复合词转换器不是在推理时一个接一个地预测与这些不同属性相对应的标记,而是将它们一起预测,这大大减少了为全长歌曲建模所需的序列长度,也使建模这些属性之间的依赖关系变得更容易。
{"title":"Automatic Music Composition with Transformers","authors":"Yi-Hsuan Yang","doi":"10.1145/3463946.3469111","DOIUrl":"https://doi.org/10.1145/3463946.3469111","url":null,"abstract":"In this talk, I will first give a brief overview of recent deep learning-based approaches for automatic music generation in the symbolic domain. I will then talk about our own research that employs self-attention based architectures, a.k.a. Transformers, for symbolic music generation. A naive approach with Transformers would treat music as a sequence of text-like tokens. But, our research demonstrates that Transformers can generate higher-quality music when music is not treated simply as text. In particular, our Pop Music Transformer model, published at ACM Multimedia 2020, employs a novel beat-based representation of music that informs self-attention models with the bar-beat metrical structure present in music. This approach greatly improves the rhythmic structure of the generated music. A more recent model we published at AAAI 2021, named the Compound Word Transformer, exploits the fact that a musical note is associated with multiple attributes such as pitch, duration and velocity. Instead of predicting tokens corresponding to these different attributes one-by-one at inference time, the Compound Word Transformer predicts them altogether jointly, greatly reducing the sequence length needed to model a full-length song and also making it easier to model the dependency among these attributes.","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90196438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposes a method to estimate a group of featured characters during an arbitrary period in comics. Comics have so many aspects of attractiveness such as illustrations and quotes. The storyline, which is one of the attractive of comics, enables us to enjoy the dramas in comics. In comics, the story is driven by characters' activities represented in multimedia forms: emotion, speech, and some other actions. This paper, as a first step to recognize the storyline, tackles the estimation of a group of featured characters in a given period. To compute the storyline of comics with the facility, the proposed method uses a sequence of characters' appearances for each page. The experiment showed that the proposed method outperformed the comparative methods in estimating groups of featured characters with a 0.82 F-value on average while comparative methods showed 0.67 and 0.48. The results showed that sequences of characters' appearance, which are relatively easy to obtain, were sufficient to catch the brief storyline i.e. featured characters in a story.
{"title":"Estimating Groups of Featured Characters in Comics with Sequence of Characters' Appearance","authors":"Kodai Imaizumi, Ryosuke Yamanishi, Yoko Nishihara, Takahiro Ozawa","doi":"10.1145/3463946.3469242","DOIUrl":"https://doi.org/10.1145/3463946.3469242","url":null,"abstract":"This paper proposes a method to estimate a group of featured characters during an arbitrary period in comics. Comics have so many aspects of attractiveness such as illustrations and quotes. The storyline, which is one of the attractive of comics, enables us to enjoy the dramas in comics. In comics, the story is driven by characters' activities represented in multimedia forms: emotion, speech, and some other actions. This paper, as a first step to recognize the storyline, tackles the estimation of a group of featured characters in a given period. To compute the storyline of comics with the facility, the proposed method uses a sequence of characters' appearances for each page. The experiment showed that the proposed method outperformed the comparative methods in estimating groups of featured characters with a 0.82 F-value on average while comparative methods showed 0.67 and 0.48. The results showed that sequences of characters' appearance, which are relatively easy to obtain, were sufficient to catch the brief storyline i.e. featured characters in a story.","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82392232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-15DOI: 10.38007/ijmc.2021.020205
{"title":"E-Commerce Personnel Training of \"Government-Industry-Enterprises-University\" Based on Computer Cloud Computing","authors":"","doi":"10.38007/ijmc.2021.020205","DOIUrl":"https://doi.org/10.38007/ijmc.2021.020205","url":null,"abstract":"","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84143562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-15DOI: 10.38007/ijmc.2021.020203
{"title":"Meta Analysis of the Effect of Nursing Intervention on Chronic Wound","authors":"","doi":"10.38007/ijmc.2021.020203","DOIUrl":"https://doi.org/10.38007/ijmc.2021.020203","url":null,"abstract":"","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84449750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-15DOI: 10.38007/ijmc.2021.020204
{"title":"Teaching Platform for Private Undergraduate Colleges and Universities Teaching Qualification Evaluation Model Based on DEL-AHP","authors":"","doi":"10.38007/ijmc.2021.020204","DOIUrl":"https://doi.org/10.38007/ijmc.2021.020204","url":null,"abstract":"","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88417603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-15DOI: 10.38007/ijmc.2021.020201
R. Recupero
With the continuous development of social economy, China's education industry is also developing. At the end of the 20th century, the emerging major, broadcast and TV director, also developed. Under the background of the popularization of quality education and the deepening of education reform, the new education model advocates students to master the methods and strategies of learning in the process of learning, and pay attention to students' ability of innovation and practice. In the education and teaching activities, the innovative and entrepreneurial education model through cooperation between schools and enterprises can promote students to improve their theoretical ability, innovation and practical ability. However, with its rapid development, there are some weak links in teaching practice. This paper proposes a new perspective on these misunderstandings and weaknesses, and introduces innovative ideas. Through the innovative research of this profession, we will achieve a higher field of educational development.
{"title":"Innovation and Entrepreneurship of Broadcast and TV Director Major from Self Media Platform","authors":"R. Recupero","doi":"10.38007/ijmc.2021.020201","DOIUrl":"https://doi.org/10.38007/ijmc.2021.020201","url":null,"abstract":"With the continuous development of social economy, China's education industry is also developing. At the end of the 20th century, the emerging major, broadcast and TV director, also developed. Under the background of the popularization of quality education and the deepening of education reform, the new education model advocates students to master the methods and strategies of learning in the process of learning, and pay attention to students' ability of innovation and practice. In the education and teaching activities, the innovative and entrepreneurial education model through cooperation between schools and enterprises can promote students to improve their theoretical ability, innovation and practical ability. However, with its rapid development, there are some weak links in teaching practice. This paper proposes a new perspective on these misunderstandings and weaknesses, and introduces innovative ideas. Through the innovative research of this profession, we will achieve a higher field of educational development.","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91250563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-15DOI: 10.38007/ijmc.2021.020202
P. Zanuttigh
Develop entrepreneurial innovation ability of university students, colleges and universities for the community, an important measure for economic education market, especially for advertising specialty training college and pay attention to their innovative ability is essential. In the exploration and research of the innovation and entrepreneurship education in advertising majors, it should be based on the research resources of advertising majors and teaching reforms, focusing on the reform of transformation curriculum reform and talent training programs, and guided by the training mechanism of innovative entrepreneurs. Gradually strengthen the deep integration of innovation and entrepreneurship education and talent training system, curriculum teaching content, practical education activities, curriculum assessment and credit assessment, so as to improve the teaching level of college advertising majors.
{"title":"The Importance and Method of Deep Integration of Innovation and Entrepreneurship Education and Advertising Education","authors":"P. Zanuttigh","doi":"10.38007/ijmc.2021.020202","DOIUrl":"https://doi.org/10.38007/ijmc.2021.020202","url":null,"abstract":"Develop entrepreneurial innovation ability of university students, colleges and universities for the community, an important measure for economic education market, especially for advertising specialty training college and pay attention to their innovative ability is essential. In the exploration and research of the innovation and entrepreneurship education in advertising majors, it should be based on the research resources of advertising majors and teaching reforms, focusing on the reform of transformation curriculum reform and talent training programs, and guided by the training mechanism of innovative entrepreneurs. Gradually strengthen the deep integration of innovation and entrepreneurship education and talent training system, curriculum teaching content, practical education activities, curriculum assessment and credit assessment, so as to improve the teaching level of college advertising majors.","PeriodicalId":43265,"journal":{"name":"International Journal of Mobile Computing and Multimedia Communications","volume":null,"pages":null},"PeriodicalIF":0.6,"publicationDate":"2021-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81244694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}